Multiple Instance Hybrid Estimator for Learning Target Signatures

TL;DR

This paper introduces a novel multiple instance hybrid estimator that learns discriminative target signatures from imprecise labels, improving hyperspectral target detection without requiring exact target signatures.

Contribution

It presents a new approach for estimating target signatures from imprecise labels within a multiple instance learning framework, enhancing detection accuracy.

Findings

Effective in simulated hyperspectral data

Demonstrates improved detection on real data

Outperforms traditional signature-based methods

Abstract

Signature-based detectors for hyperspectral target detection rely on knowing the specific target signature in advance. However, target signature are often difficult or impossible to obtain. Furthermore, common methods for obtaining target signatures, such as from laboratory measurements or manual selection from an image scene, usually do not capture the discriminative features of target class. In this paper, an approach for estimating a discriminative target signature from imprecise labels is presented. The proposed approach maximizes the response of the hybrid sub-pixel detector within a multiple instance learning framework and estimates a set of discriminative target signatures. After learning target signatures, any signature based detector can then be applied on test data. Both simulated and real hyperspectral target detection experiments are shown to illustrate the effectiveness of the method.